{"id":"W4220991771","doi":"10.1145/3506712","title":"Machine Learning and Data Cleaning: Which Serves the Other?","year":2022,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data quality; Software deployment; Data science; Data integration; Quality (philosophy); Data mining; Software engineering; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03712774,0.00006679204,0.0001770647,0.0001204452,0.0005756235,0.0006932159,0.002255425,0.00001533967,0.0003052047],"category_scores_gemma":[0.004194206,0.0000394428,0.00001553522,0.0003377476,0.00005433148,0.01148219,0.004536374,0.0003438487,0.000009422397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001065444,"about_ca_system_score_gemma":0.00004877463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001334627,"about_ca_topic_score_gemma":0.00007638036,"domain_scores_codex":[0.9964837,0.0009377451,0.001119888,0.000140904,0.001221735,0.00009602017],"domain_scores_gemma":[0.9966832,0.0008370957,0.001219966,0.001033531,0.0001637226,0.00006246823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002824105,0.00008347175,0.01844502,0.00006799703,0.0001217814,0.000001689628,0.008681733,0.000246043,0.0000101267,0.04906906,0.1241074,0.7988833],"study_design_scores_gemma":[0.0003201442,0.00006536437,0.009375265,0.000004142163,0.00001471903,0.00003017954,0.0165838,0.01522554,8.959233e-7,0.001708266,0.9566145,0.00005720624],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4901774,0.006268912,0.2013952,0.2317124,0.003149207,0.001461066,0.03510616,0.0001282592,0.03060134],"genre_scores_gemma":[0.9914062,0.0006906645,0.001637916,0.004695772,0.0001155206,0.000001289817,0.001179164,0.000004722156,0.0002687688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8325071,"threshold_uncertainty_score":0.9914796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3220743629101961,"score_gpt":0.472009332225758,"score_spread":0.1499349693155619,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}